Journal article icon

Journal article

Machine learning line bundle cohomology

Abstract:

We investigate different approaches to machine learning of line bundle cohomology on complex surfaces as well as on Calabi-Yau three-folds. Standard function learning based on simple fully connected networks with logistic sigmoids is reviewed and its main features and shortcomings are discussed. It has been observed recently that line bundle cohomology can be described by dividing the Picard lattice into certain regions in each of which the cohomology dimension is described by a polynomial fo...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1002/prop.201900087

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Physics
Sub department:
Theoretical Physics
Role:
Author
ORCID:
0000-0002-0861-5363
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Physics
Sub department:
Theoretical Physics
Oxford college:
Balliol College
Role:
Author
ORCID:
0000-0002-3025-1922
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Physics
Sub department:
Theoretical Physics
Oxford college:
Balliol College
Role:
Author
ORCID:
0000-0003-4969-0447
Publisher:
Wiley
Journal:
Fortschritte der Physik More from this journal
Volume:
68
Issue:
1
Article number:
1900087
Publication date:
2019-12-27
Acceptance date:
2019-10-16
DOI:
EISSN:
1521-3978
ISSN:
0015-8208
Language:
English
Keywords:
Pubs id:
1023063
Local pid:
pubs:1023063
Deposit date:
2021-08-04

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP